summaryrefslogtreecommitdiff
path: root/drivers/edac
diff options
context:
space:
mode:
authorRobert Richter <rrichter@marvell.com>2019-11-06 12:33:23 +0300
committerBorislav Petkov <bp@suse.de>2019-11-10 14:40:14 +0300
commit7088e29e0423d3195e09079b4f849ec4837e5a75 (patch)
treeaf8e23ab26d5d97fabcce53b64f19d5f206424b8 /drivers/edac
parent7c1049317042a37638788bb8a892dbd75b742655 (diff)
downloadlinux-7088e29e0423d3195e09079b4f849ec4837e5a75.tar.xz
EDAC/ghes: Fix grain calculation
The current code to convert a physical address mask to a grain (defined as granularity in bytes) is: e->grain = ~(mem_err->physical_addr_mask & ~PAGE_MASK); This is broken in several ways: 1) It calculates to wrong grain values. E.g., a physical address mask of ~0xfff should give a grain of 0x1000. Without considering PAGE_MASK, there is an off-by-one. Things are worse when also filtering it with ~PAGE_MASK. This will calculate to a grain with the upper bits set. In the example it even calculates to ~0. 2) The grain does not depend on and is unrelated to the kernel's page-size. The page-size only matters when unmapping memory in memory_failure(). Smaller grains are wrongly rounded up to the page-size, on architectures with a configurable page-size (e.g. arm64) this could round up to the even bigger page-size of the hypervisor. Fix this with: e->grain = ~mem_err->physical_addr_mask + 1; The grain_bits are defined as: grain = 1 << grain_bits; Change also the grain_bits calculation accordingly, it is the same formula as in edac_mc.c now and the code can be unified. The value in ->physical_addr_mask coming from firmware is assumed to be contiguous, but this is not sanity-checked. However, in case the mask is non-contiguous, a conversion to grain_bits effectively converts the grain bit mask to a power of 2 by rounding it up. Suggested-by: James Morse <james.morse@arm.com> Signed-off-by: Robert Richter <rrichter@marvell.com> Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org> Cc: "linux-edac@vger.kernel.org" <linux-edac@vger.kernel.org> Cc: Tony Luck <tony.luck@intel.com> Link: https://lkml.kernel.org/r/20191106093239.25517-11-rrichter@marvell.com
Diffstat (limited to 'drivers/edac')
-rw-r--r--drivers/edac/ghes_edac.c10
1 files changed, 8 insertions, 2 deletions
diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index 5dc53d3512ae..e24fbbac5556 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -230,6 +230,7 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
/* Cleans the error report buffer */
memset(e, 0, sizeof (*e));
e->error_count = 1;
+ e->grain = 1;
strcpy(e->label, "unknown label");
e->msg = pvt->msg;
e->other_detail = pvt->other_detail;
@@ -325,7 +326,7 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
/* Error grain */
if (mem_err->validation_bits & CPER_MEM_VALID_PA_MASK)
- e->grain = ~(mem_err->physical_addr_mask & ~PAGE_MASK);
+ e->grain = ~mem_err->physical_addr_mask + 1;
/* Memory error location, mapped on e->location */
p = e->location;
@@ -441,8 +442,13 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
if (p > pvt->other_detail)
*(p - 1) = '\0';
+ /* Sanity-check driver-supplied grain value. */
+ if (WARN_ON_ONCE(!e->grain))
+ e->grain = 1;
+
+ grain_bits = fls_long(e->grain - 1);
+
/* Generate the trace event */
- grain_bits = fls_long(e->grain);
snprintf(pvt->detail_location, sizeof(pvt->detail_location),
"APEI location: %s %s", e->location, e->other_detail);
trace_mc_event(type, e->msg, e->label, e->error_count,